Assessing Hospitalization for SARS-CoV-2 Confirmed Cases by a Cross-Entropy Weighted Ensemble Classifier

The potential need of hospitalization for patients with acute respiratory COVID-19 infection caused by the SARS-CoV2 virus is a critical decision, as it has a direct effect on the potential response. In addition, it leads to an allocation of resources (bed, care, and medical personnel) that, given the pandemic, are limited. According to official information reported since March 1, 2020 and updated to June 30, 2021, an ensemble of classifiers weighted by the cross-entropy information measure is proposed. We considered data based on the knowledge of a set of features before a wide availability of vaccines or identified variants of the virus were present. The aim is to contribute toward the enhancement of a better-informed assessment of risk by the general population when exposed to the disease in the aforementioned period. The results show an improvement in the detection of cases susceptible to hospitalization, with an accuracy of 91.46%, and in a restrictive scenario, there is a preventive alert to patients, even though under the established criteria should not be admitted, to remain under monitoring to anticipate the evolution of the disease to a severe stage. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Optimized method of subset generation for ensemble classification

Multiclass learning problems involve training classification models to accurately classify data instances into class labels. The number of class labels that are incorporated in a classification model directly affects its training time and accuracy. It has been noted that the existing models, when used on larger datasets having an extensive number of classes, often fail in achieving an accuracy usable for functional, real-world scenarios and tend to overfit on training data. Present research attempts to optimize the performance of classifiers by creating custom classification strategies, and neural network architectures for specific classification tasks and datasets. The efficiency of one such optimization of classifiers, classifier ensembles can further be improved by altering methods of subset generation from the dataset and correspondingly, class prediction. In this regard, we propose a method of constructing ensembles which aims to increase the accuracy of any given classifier while reducing training time by using a two step approach- one step for group formation as a part of constructing ensembles, and another for relative probability calculations which combines the result of ensembles. The proposed method is implemented and experiments are done on the Fashion MNIST (10 class labels), NIH Chest X-Ray + COVID-19 (16 class labels), Kuzushiji-49 (49 class labels), and CIFAR-100 (100 class labels) datasets. Experimental results show the efficacy of the proposed method which has achieved an increase of 6.33%, 9.32%, 8.59%, and 12.27% in accuracies of respective datasets and at the end, results are debated. © 2021 IEEE.